Triple

T15117017
Position Surface form Disambiguated ID Type / Status
Subject Telecom Tower E361066 entity
Predicate operator P179 FINISHED
Object Telstra E277056 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Telstra | Statement: [Telecom Tower, operator, Telstra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Telstra
Context triple: [Telecom Tower, operator, Telstra]
  • A. Telstra chosen
    Telstra is Australia's largest telecommunications and media company, providing mobile, internet, and other communication services nationwide.
  • B. Optus
    Optus is a major Australian telecommunications company providing mobile, internet, and related communication services nationwide.
  • C. Telewest
    Telewest was a major UK cable television, broadband, and telecommunications provider that later became part of Virgin Media through a merger.
  • D. TelstraClear
    TelstraClear was a major New Zealand telecommunications company that provided phone, internet, and pay TV services before being acquired by Vodafone.
  • E. NewTel Communications
    NewTel Communications was a regional telecommunications company in Atlantic Canada that later became part of Bell Aliant through industry consolidation.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d85a0491ec8190830960be8fafb994 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0059ca9048190b742e70e818ee64f completed April 15, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69fec87ce9808190a862ac5839272711 completed May 9, 2026, 5:39 a.m.
Created at: April 10, 2026, 3:05 a.m.